通过压缩残差减少扩散模型并行推理通信开销，显著提速且保持生成质量。
Accelerating Parallel Diffusion Model Serving with Residual Compression
- 仅传输相邻步骤间激活差异的残差压缩，大幅降低通信数据量。
- 在4xL20上实现3.0倍加速，序列并行在慢网下达6.7倍速度提升。
- 兼容多种模型与并行策略，无需重构流水线，易部署于实际系统。
扩散模型生成逼真图像与视频，但需大量计算资源，实时部署依赖多加速器并行。然而并行推理引入大量设备间激活数据交换，造成显著通信开销，制约效率与可扩展性。本文提出CompactFusion压缩框架，显著减少通信量同时保持生成质量。核心观察发现：扩散激活具有强时间冗余性——相邻步骤生成高度相似激活，饱和带宽却携带极少新信息。为此，我们寻求更紧凑表示以编码关键信息。CompactFusion采用残差压缩，仅传输压缩后的步骤间激活差异。基于实证分析与理论证明，该方法有效剔除冗余数据，实现大幅数据缩减且保持高保真度。同时集成轻量级误差反馈机制，防止误差累积。CompactFusion开创并行扩散推理新范式，在4xL20配置下实现3.0倍加速，显著优于先前方法；在慢网络下支持通信密集型策略如序列并行，较以往重叠法提升6.7倍速度。该方案广泛适配各类扩散模型与并行场景，无需流水线重构，实现简便。基于xDiT的可移植实现已公开于https://github.com/Cobalt-27/CompactFusion。
原文摘要 · Abstract (English)
Diffusion models produce realistic images and videos but require substantial computational resources, necessitating multi-accelerator parallelism for real-time deployment. However, parallel inference introduces significant communication overhead from exchanging large activations between devices, limiting efficiency and scalability. We present CompactFusion, a compression framework that significantly reduces communication while preserving generation quality. Our key observation is that diffusion activations exhibit strong temporal redundancy-adjacent steps produce highly similar activations, saturating bandwidth with near-duplicate data carrying little new information. To address this inefficiency, we seek a more compact representation that encodes only the essential information. CompactFusion achieves this via Residual Compression that transmits only compressed residuals (step-wise activation differences). Based on empirical analysis and theoretical justification, we show that it effectively removes redundant data, enabling substantial data reduction while maintaining high fidelity. We also integrate lightweight error feedback to prevent error accumulation. CompactFusion establishes a new paradigm for parallel diffusion inference, delivering lower latency and significantly higher generation quality than prior methods. On 4xL20, it achieves 3.0x speedup while greatly improving fidelity. It also uniquely supports communication-heavy strategies like sequence parallelism on slow networks, achieving 6.7x speedup over prior overlap-based method. CompactFusion applies broadly across diffusion models and parallel settings, and integrates easily without requiring pipeline rework. Portable implementation demonstrated on xDiT is publicly available at https://github.com/Cobalt-27/CompactFusion
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。